Investigating the spatiotemporal dynamics of the human brain is a complex challenge due to the intricate nature of brain networks, and the limitations of current analytical methods. Herein, we introduce the 4D functional Magnetic Resonance Imaging (fMRI) CrossFormer (4DfCF), a novel vision transformer architecture designed to process high-dimensional 4D fMRI data. This model integrates temporal and spatial dimensions to effectively learn and predict cognitive and clinical outcomes. We further evaluated the 4DfCF on three benchmark datasets: Attention Deficit Hyperactivity Disorder-200 (ADHD-200), Alzheimer's Disease Neuroimaging Initiative (ADNI), and Autism Brain Imaging Data Exchange (ABIDE). The results showed that our model consistently outperforms state-of-the-art baseline models, achieving an accuracy improvement of 5-10%, a precision increase of 4-8%, a recall enhancement of 6-9%, and an F1-score boost of 7-11% . Additionally, the 4D fMRI CrossFormer-Tiny variant demonstrated greater efficiency than existing methods, using 20% fewer computational resources and achieving 30% faster training times. Pre-training experiments further reveal that models pre-trained on one dataset and fine-tuned on another achieved faster convergence and higher accuracy, with the Autism Brain Imaging Data Exchange (ABIDE) pre-trained models showing the best performance. Additionally, we employed an explainable AI method to identify the brain regions associated with disease diagnosis. Overall, our findings highlight the potential of the 4DfCF to advance precision neuroscience through efficient and scalable analysis of complex fMRI data.

Wastewater treatment plants (WWTPs) are among the most energy-intensive components of urban infrastructure and bear strict regulatory responsibilities for wastewater quality. These dual challenges, minimizing energy consumption and maintaining environmental compliance, are deeply interrelated and must be managed simultaneously to achieve sustainable plant operation. This study proposes a framework that comprises two customized components. The first component employs a voting ensemble model based on transformer architecture to predict energy consumption. It processes heterogeneous feature domains — including hydraulic, wastewater, and climatic variables — through parallel attention-driven streams. The outputs from these streams are then aggregated using a weighted voting mechanism to produce the final prediction. Second, a multitask Bidirectional Gated Recurrent Unit (Bi-GRU) forecasts wastewater quality indicators concurrently (ammonia, Biochemical Oxygen Demand (BOD), and Chemical Oxygen Demand (COD)), capturing shared temporal dependencies and reducing model complexity. A hybrid preprocessing strategy is applied, incorporating domain-aware outlier detection (z-score and Interquartile Range (IQR)), K-Nearest Neighbors (KNN) Imputation, and feature selection using Extreme Gradient Boosting (XGBoost). Experimental results showed that. The voting ensemble model achieved the best results for energy consumption prediction with 31.61 of Root Mean Squared Error (RMSE). The multitask Bi-GRU achieved the best results for wastewater quality indicators with RMSE at 6.1689, 48.0323, and 88.2214 for ammonia, BOD, and COD, respectively. This work is among the first to integrate transformer ensembles and multitask learning in a unified WWTP forecasting system. Simultaneously addressing energy efficiency and water quality assurance, this offers a practical, scalable, and intelligent decision-support tool for sustainable wastewater management.

The rise of the Internet of Things (IoT) has significantly transformed Industrial Control Systems (ICS) by increasing their dependence on interconnected devices for automating processes. This growing integration of IoT technologies within ICS has heightened concerns about security and privacy, underscoring the importance of protecting sensitive data. This paper addresses the challenge of detecting anomalies within ICS environments that utilize the Modbus protocol. Modbus requests are encapsulated in Modbus frames, which direct devices on the specific actions to undertake. Thus, the sequence of Modbus frames in network traffic serves as a comprehensive indicator of device behavior on the network. To tackle this challenge, we introduce a novel approach for anomaly detection by modeling device interactions on the network through the analysis of Modbus frame sequences using a Non-deterministic Finite Automaton (NFA) framework, termed the Modbus-NFA Behavior Distinguisher (MNBD) model. The NFA framework is particularly effective for this purpose as it can represent multiple potential states and transitions within a network, thereby capturing the complexity and variability of network behaviors. This capability allows the MNBD model to detect deviations from normal behavior, identifying potential anomalies with high accuracy. Our MNBD model was evaluated against several existing ICS network traffic datasets. The results demonstrate that the Modbus-NFA approach not only surpasses traditional machine learning models but also outperforms sequence-based deep learning models . Additionally, cross-dataset testing reveals that the MNBD model exhibits superior generalization capabilities compared to deep learning-based approaches. These findings highlight the MNBD model’s potential as a robust tool for anomaly detection, advancing research and development efforts in ICS security.

Abstract Unmanned aerial vehicles are rapidly being utilized in surveillance and traffic monitoring because of their great mobility and capacity to cover regions at various elevations and positions. It is a challenging task to detect vehicles due to their various shapes, textures, and colors. One of the most difficult challenges is correctly detecting and counting aerial view vehicles in real time for traffic monitoring objectives using aerial images and videos. In this research, strategies are presented for improving the detection ability of self-driving vehicles in tough conditions, also for traffic monitoring, vehicle surveillance. We make classification, tracking trajectories, and movement calculation where fog, sandstorm (dust), and snow conditions are challenging. Initially, image enhancement methods are implemented to improve unclear images of roads. The improved images are then subjected to an object detection and classification algorithm to detect vehicles. Finally, new methods were evaluated (Corrected Optical flow/Corrected Kalman filter) to get the least error of trajectories. Also features like vehicle count, type, tracking trajectories by (Optical flow, Kalman Filter, Euclidean Distance) and relative movement calculation are extracted from the coordinates of the observed objects. These techniques aim to improve vehicle detection, tracking, and movement over aerial views of roads especially in bad weather. As a result, for aerial view vehicles in bad weather, our proposed method has an error of less than 5 pixels from the actual value and give the best results. This improves detection and tracking performance for aerial view vehicles in bad weather conditions.

In a hospital, accurate and rapid mortality prediction of Length of Stay (LOS) is essential since it is one of the essential measures in treating patients with severe diseases. When predictions of patient mortality and readmission are combined, these models gain a new level of significance. Therefore, the most expensive components of patient care are LOS and readmission rates. Several studies have assessed readmission to the hospital as a single-task issue. The performance, robustness, and stability of the model increase when many correlated tasks are optimized. This study develops multimodal multitasking Long Short-Term Memory (LSTM) Deep Learning (DL) model that can predict both LOS and readmission for patients using multi-sensory data from 47 patients. Continuous sensory data is divided into eight sections, each of which is recorded for an hour. The time steps are constructed using a dual 10-second window-based technique, resulting in six steps per hour. The 30 statistical features are computed by transforming the sensory input into the resulting vector. The proposed multitasking model predicts 30-day readmission as a binary classification problem and LOS as a regression task by constructing discrete time-step data based on the length of physical activity during a hospital stay. The proposed model is compared to a random forest for a single-task problem (classification or regression) because typical machine learning algorithms are unable to handle the multitasking challenge. In addition, sensory data combined with other cost-effective modalities such as demographics, laboratory tests, and comorbidities to construct reliable models for personalized, cost-effective, and medically acceptable prediction. With a high accuracy of 94.84%, the proposed multitask multimodal DL model classifies the patient's readmission status and determines the patient's LOS in hospital with a minimal Mean Square Error (MSE) of 0.025 and Root Mean Square Error (RMSE) of 0.077, which is promising, effective, and trustworthy.